valvin
/
ttrss
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #304 from wltb/feedparser_xml9 

Feedparser: Change error handling a bit
This commit is contained in:
Andrew Dolgov 2013-09-25 03:25:34 -07:00
parent c6e089b969 d3305ff8de
commit f227d0af28
1 changed files with 35 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
classes/feedparser.php
View File

@ -23,18 +23,12 @@ class FeedParser {
$error = libxml_get_last_error();
// libxml compiled without iconv?
if ($error && ($error->code == 32 || $error->code == 9)) {
if (preg_match('/^(<\?xml[\t\n\r ].*?encoding=["\'])(.+?)(["\'].*?\?>)/s', $data, $matches) === 1) {
$enc = $matches[2];
$data = mb_convert_encoding($data, 'UTF-8', $enc);
if ($error && $error->code == 32) {
if (preg_match('/^(<\?xml[\t\n\r ].*?encoding[\t\n\r ]*=[\t\n\r ]*["\'])(.+?)(["\'].*?\?>)/s', $data, $matches) === 1) {
$data = mb_convert_encoding($data, 'UTF-8', $matches[2]);
$data = preg_replace('/^<\?xml[\t\n\r ].*?\?>/s', $matches[1] . "UTF-8" . $matches[3] , $data);
// apparently not all UTF-8 characters are valid for XML
$data = preg_replace('/[^\x{0009}\x{000a}\x{000d}\x{0020}-\x{D7FF}\x{E000}-\x{FFFD}]+/u', ' ', $data);
if ($data) {
libxml_clear_errors();
@ -43,24 +37,41 @@ class FeedParser {
$error = libxml_get_last_error();
}
}
}
// some terrible invalid unicode entity?
if ($error && $error->code == 9) {
$data = mb_convert_encoding($data, 'UTF-8', 'UTF-8');
if ($data) {
libxml_clear_errors();
$this->doc = new DOMDocument();
$this->doc->loadXML($data);
$error = libxml_get_last_error();
}
}
$this->error = $this->format_error($error);
// some terrible invalid unicode entity?
if ($error) {
foreach(libxml_get_errors() as $err) {
if ($err->code == 9) {
// remove dangling bytes
$data = mb_convert_encoding($data, 'UTF-8', 'UTF-8');
// apparently not all UTF-8 characters are valid for XML
$data = preg_replace('/[^\x{0009}\x{000a}\x{000d}\x{0020}-\x{D7FF}\x{E000}-\x{FFFD}]+/u', ' ', $data);
if ($data) {
libxml_clear_errors();
$this->doc = new DOMDocument();
$this->doc->loadXML($data);
$error = libxml_get_last_error();
}
break;
}
}
}
$this->error = "";
if($error) {
foreach(libxml_get_errors() as $error) {
if($error->level == LIBXML_ERR_FATAL) {
$this->error = $this->format_error($error);
break; //break here because currently we only show one error
}
}
}
libxml_clear_errors();
$this->items = array();